© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 60338
    Prev
    Next
    INDEX
    Explanations

    elements of religious or spiritual significance and kindness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Manip
    -0.09
     Succ
    -0.07
    anguard
    -0.07
     gdk
    -0.07
     Ramp
    -0.07
    orrent
    -0.06
    _mk
    -0.06
     ìķĶ
    -0.06
    ovice
    -0.06
    iren
    -0.06
    POSITIVE LOGITS
    allest
    0.07
     mystery
    0.06
    ahren
    0.06
     works
    0.06
     workings
    0.06
    fur
    0.06
    Jar
    0.06
     distance
    0.06
    ercul
    0.06
     magn
    0.06
    Activations Density 0.013%

    No Known Activations